Darko Musicki

Integrated probabilistic data association

This paper presents an integrated probabilistic data association algorithm which provides recursive formulas for both data association and track quality (probability of track existence), allowing track initiation and track termination to be fully integrated into the association and smoothing algorithm. Integrated probabilistic data association is of similar computational complexity to probabilistic data association and as demonstrated by simulation, achieves comparable performance to the more computationally expensive interactive multiple model probabilistic data association algorithm which also integrates initiation and tracking. >

Joint integrated probabilistic data association: JIPDA

A new recursive filter for multi-target tracking in clutter is presented. Multiple tracks may share the same measurement(s). Joint events are formed by creating all possible combinations of track-measurement assignments and the probabilities for these joint events are calculated. The expressions for the joint event probabilities incorporate the probabilities of target existence of individual tracks, an efficient approximation for the cluster volume and a priori probability of the number of clutter measurements in each cluster. From these probabilities the data association and target existence probabilities of individual tracks are obtained, which allows track state update and false track discrimination. A simulation study is presented to show the effectiveness of this approach.

Joint Integrated Probabilistic Data Association - JIPDA

This paper presents a new algorithm for multi-target tracking. In multi-target situations, multiple tracks may share the same measurement(s). Joint events are formed by creating all possible combinations of track-measurement assignments. The probabilities for these joint events are calculated The expressions for the joint events incorporate the probabilities of track existence of individual tracks, as well as an efficient approximation for the cluster volume and an a-priori probability of the number of clutter measurements in each cluster. From these probabilities the data association and track existence probabilities of individual tracks are obtained These probabilities will allow track update in the classic PDA fashion, as well as automatic track initiation, maintenance and termination. The JIPDA algorithm is recursive and integrates seamlessly with the IPDA algorithm. Simulations are used to verify the performance of the algorithm and compare it with the per performance of the IPDA, IPDA-DLL and IJPDA algorithms in a dense and non-homogenous clutter environment, in crossing target situations.

Integrated probabilistic data association (IPDA)

A version of the probabilistic data association (PDA) algorithm that is called integrated probabilistic data association (IPDA) is presented. Rather than deriving algorithms based on an assumption of track existence, IPDA starts from expressions which treat track existence as an event with an associated probability. This approach leads to a set of recursive formulae for both data association and probability of track existence or track quality. This is useful in the track initiation phase (to confirm a tentative track) and in track termination (to terminate a false track). The IPDA algorithm is compared with both the probabilistic data association algorithm (PDA) and the interactive multiple model (IMM) PDA algorithm.<<ETX>>

Mobile Emitter Geolocation and Tracking Using TDOA and FDOA Measurements

This paper considers recursive tracking of one mobile emitter using a sequence of time difference of arrival (TDOA) and frequency difference of arrival (FDOA) measurement pairs obtained by one pair of sensors. We consider only a single emitter without data association issues (no missed detections or false measurements). Each TDOA measurement defines a region of possible emitter locations around a unique hyperbola. This likelihood function is approximated by a Gaussian mixture, which leads to a dynamic bank of Kalman filters tracking algorithm. The FDOA measurements update relative probabilities and estimates of individual Kalman filters. This approach results in a better track state probability density function approximation by a Gaussian mixture, and tracking results near the Cramer-Rao lower bound. Proposed algorithm is also applicable in other cases of nonlinear information fusion. The performance of proposed Gaussian mixture approach is evaluated using a simulation study, and compared with a bank of EKF filters and the Cramer-Rao lower bound.

Integrated track splitting filter - efficient multi-scan single target tracking in clutter

A fully automatic tracking algorithm must be able to deal with an unknown number of targets, unknown target initiation and termination times, false measurements and possibly time-varying target trajectory behaviour. An efficient algorithm for tracking in this environment is presented here. This approach makes use of estimates of the probability of target existence, which is an integral part of the algorithm. This allows for the efficient generation and management of possible target hypotheses, yielding an algorithm with performance that matches what can be obtained by multiple hypothesis tracking-based approaches, but at a significantly lower computational cost. This paper considers only the single target case for clarity. The extension to multiple targets is easily incorporated into this framework. Simulation studies are given that show the effectiveness of this approach in the presence of heavy and nonuniform clutter when tracking a target in an environment of low probability of detection and in an environment where the target performs violent manoeuvres.

Clutter map information for data association and track initialization

This paper considers the problem of forming and maintaining tracks when measurements have both uncertain origin and are corrupted by additive sensor noise. The spatial clutter measurement density is assumed nonhomogeneous and known. The PPDA-MAP algorithm provides a set of recursive formulae for data association and probability of target existence, thus enabling automatic track initiation, track maintenance, and track termination. New values for initial probability of target existence for IPDA-type algorithm are also derived. Simulation results compare the performance of IPDA-MAP with IPDA, IMM-PDA, IMM-PDA-MAP, EB-PDA and EB-PDA-MAP in a heavy and nonuniform clutter situation.

Tracking in clutter using IMM-IPDA-based algorithms

We describe three single-scan probabilistic data association (PDA) based algorithms for tracking manoeuvering targets in clutter. These algorithms are derived by integrating the interacting multiple model (IMM) estimation algorithm with the PDA approximation. Each IMM model a posteriori state estimate probability density function (pdf) is approximated by a single Gaussian pdf. Each algorithm recursively updates the probability of target existence, in the manner of integrated PDA (IPDA). The probability of target existence is a track quality measure, which can be used for false track discrimination. The first algorithm presented, IMM-IPDA, is a single target tracking algorithm. Two multitarget tracking algorithms are also presented. The IMM-JIPDA algorithm calculates a posteriori probabilities of all measurement to track allocations, in the manner of the joint IPDA (JIPDA). The number of measurement to track allocations grows exponentially with the number of shared measurements and the number of tracks which share the measurements. Therefore, IMM-JIPDA can only be used in situations with a small number of crossing targets and low clutter measurement density. The linear multitarget IMM-IPDA (IMM-LMIPDA) is also a multitarget tracking algorithm, which achieves the multitarget capabilities by integrating linear multitarget (LM) method with IMM-IPDA. When updating one track using the LM method, the other tracks modulate the clutter measurement density and are subsequently ignored. In this fashion, LM achieves multitarget capabilities using the number of operations which are linear in the: number of measurements and the number of tracks, and can be used in complex scenarios, with dense clutter and a large number of targets.

Adaptive Clutter Measurement Density Estimation for Improved Target Tracking

In a surveillance situation the origin of each measurement is uncertain. Each measurement may be a false (clutter) measurement, or it may be a target detection. Probabilistic methods are usually used to discriminate between the clutter and the target measurements. Clutter measurement density is an important parameter in this process. The values of the clutter measurement density in the surveillance space are rarely known a priori, and are usually estimated using sensor data and track information. A novel approach is presented and evaluated for estimating the values of clutter measurement density, which significantly enhances target tracking. Simulation results validate this approach.

Multiscan Multitarget Tracking in Clutter with Integrated Track Splitting Filter

A fully automatic tracking algorithm must be able to deal with an unknown number of targets, unknown target initiation and termination times, false measurements and possibly time-varying target trajectory behaviour. The approach presented in this paper follows the previously published integrated track splitting (ITS) framework which integrates a recursive calculation of the probability of target existence with multiscan trajectory estimation. This paper combines this framework with two multitarget tracking techniques. The first technique, joint multitarget tracking, enumerates and evaluates all feasible global measurement to track assignments resulting in a conditionally optimal but potentially computationally expensive technique. The second technique, linear multitarget (LM), achieves multitarget functionality by modulating clutter measurement density. LM is a suboptimal, but computationally very efficient technique. A simulation study is presented to show the effectiveness of this approach in the presence of nonuniform clutter when tracking targets in an environment where the targets perform violent manoeuvres.